Related papers: PartNeRF: Generating Part-Aware Editable 3D Shapes…

Generating photorealistic images with controllable camera pose and scene contents is essential for many applications including AR/VR and simulation. Despite the fact that rapid progress has been made in 3D-aware generative models, most…

This paper presents a novel approach to inpainting 3D regions of a scene, given masked multi-view images, by distilling a 2D diffusion model into a learned 3D scene representation (e.g. a NeRF). Unlike 3D generative methods that explicitly…

Recently, the editing of neural radiance fields (NeRFs) has gained considerable attention, but most prior works focus on static scenes while research on the appearance editing of dynamic scenes is relatively lacking. In this paper, we…

Recent work has shown the ability to learn generative models for 3D shapes from only unstructured 2D images. However, training such models requires differentiating through the rasterization step of the rendering process, therefore past work…

Novel view synthesis has recently made significant progress with the advent of Neural Radiance Fields (NeRF). DietNeRF is an extension of NeRF that aims to achieve this task from only a few images by introducing a new loss function for…

Utilizing multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work, we introduce a Generalizable Semantic Neural Radiance Field (GSNeRF), which…

We propose NeRFiller, an approach that completes missing portions of a 3D capture via generative 3D inpainting using off-the-shelf 2D visual generative models. Often parts of a captured 3D scene or object are missing due to mesh…

We present radiance field propagation (RFP), a novel approach to segmenting objects in 3D during reconstruction given only unlabeled multi-view images of a scene. RFP is derived from emerging neural radiance field-based techniques, which…

Representing a 3D shape with a set of primitives can aid perception of structure, improve robotic object manipulation, and enable editing, stylization, and compression of 3D shapes. Existing methods either use simple parametric primitives…

Creating artistic 3D scenes can be time-consuming and requires specialized knowledge. To address this, recent works such as ARF, use a radiance field-based approach with style constraints to generate 3D scenes that resemble a style image…

We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model learns to synthesize a corresponding image from different…

Large-scale 3D scene reconstruction and novel view synthesis are vital for autonomous vehicles, especially utilizing temporally sparse LiDAR frames. However, conventional explicit representations remain a significant bottleneck towards…

We propose GazeNeRF, a 3D-aware method for the task of gaze redirection. Existing gaze redirection methods operate on 2D images and struggle to generate 3D consistent results. Instead, we build on the intuition that the face region and…

Numerous diffusion models have recently been applied to image synthesis and editing. However, editing 3D scenes is still in its early stages. It poses various challenges, such as the requirement to design specific methods for different…

Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images. Despite its impressive performance, NeRF is plagued by its necessity for numerous calibrated views and its…

We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details, especially in…

We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects…

We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields involves optimizing the representation…

3D shape editing is widely used in a range of applications such as movie production, computer games and computer aided design. It is also a popular research topic in computer graphics and computer vision. In past decades, researchers have…

3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints. Existing methods often decompose 3D shapes into a sequence of localized components, treating each element in isolation without…